github yetone/magpie-releases v0.1.876
magpie v0.1.876

latest releases: v0.1.4657, v0.1.4656, v0.1.4655...
one month ago

Features

  • Added a Max output field to the provider editor, shown next to the Context window, so model reply limits can be set directly in the UI.
  • Saving the provider editor now applies the configured output limits to /v1/models, agent max tokens, and the gateway’s per-member clamp.

Improvements

  • The Max output field accepts the same compact format as the Context window, such as 32k for all models or gpt-6=128k.
  • Limits not listed in the field are dropped, and models not listed by the provider are refused.
  • Added Chinese and Japanese translations for the new field.

Install

Download from usemagpie.ai, or curl -fsSL https://usemagpie.ai/install.sh | sh. An installed magpie updates itself.

  • macOS (Apple Silicon): magpie-darwin-arm64.dmg
  • macOS (Intel): magpie-darwin-amd64.dmg
  • Windows: magpie-windows-amd64.exe (ARM: magpie-windows-arm64.exe)
  • Linux: magpie-linux-amd64 / magpie-linux-arm64 (needs GTK 3 and WebKitGTK 4.1)
  • Terminal only: magpie-cli-<os>-<arch>

功能

  • 在提供商编辑器中添加了 最大输出 字段,显示在上下文窗口旁边,因此可以直接在 UI 中设置模型回复上限。
  • 保存提供商编辑器现在会将配置的输出上限应用于 /v1/models、代理最大令牌数以及网关的每成员钳制值。

改进

  • 最大输出字段接受与上下文窗口相同的紧凑格式,例如 32k 用于所有模型,或 gpt-6=128k。
  • 该字段中未列出的上限将被丢弃,提供商未列出的模型将被拒绝。
  • 为新增字段添加了中文和日文翻译。

安装

从 usemagpie.ai 下载,或运行 curl -fsSL https://usemagpie.ai/install.sh | sh。已安装的 magpie 会自动更新。

Don't miss a new magpie-releases release

NewReleases is sending notifications on new releases.